Vulnerability assessment and security configuration activities are heavily reliant on expert knowledge. This requirement often results in many systems being left insecure due to a lack of analysis expertise and access to specialist resources. It has long been known that a system’s event logs provide historical information depicting potential security breaches, as well as recording configuration activities. However, identifying and utilising knowledge within the event logs is challenging for the non-expert. In this paper, a novel technique is developed to process security event logs of a computer that has been assessed and configured by a security professional, extract key domain knowledge indicative of their expert decision making, and automatically apply learnt knowledge to previously unseen systems by non-experts. The technique converts event log entries into an object-based model and dynamically extracts associative rules. The rules are further improved in terms of quality using a temporal metric to autonomously establish temporal-association rules and acquire a domain model of expert configuration tasks. The acquired domain model and problem instance generated from a previously unseen system can then be used to produce a plan-of-action, which can be exploited by non-professionals to improve their system’s security. Empirical analysis is subsequently performed on 20 event logs, where identified plan traces are discussed in terms of accuracy and performance.
FingerprintDive into the research topics of 'Eliciting and utilising knowledge for security event log analysis: an association rule mining and automated planning approach'. Together they form a unique fingerprint.
- Department of Computer Science - Professor
- School of Computing and Engineering
- Centre for Cybersecurity - Director
- Sustainable Living Research Centre - Member
- Centre for Planning, Autonomy and Representation of Knowledge - Associate Member
- Secure Societies Institute - Associate Member
- Centre for Biomimetic Societal Futures